{"id":"W7015310510","doi":"","title":"A Study of Augmentation-Sensitivity in Reinforcement Learning","year":2025,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Reinforcement; Control (management); Action (physics); Stability (learning theory)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004354511,0.0006292282,0.00116341,0.0006384599,0.0005708296,0.001902356,0.001372127,0.001221235,0.004593015],"category_scores_gemma":[0.05405394,0.0007489991,0.001056176,0.0007390516,0.002954846,0.003751794,0.001802476,0.003496673,0.0001470203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001469216,"about_ca_system_score_gemma":0.0009187112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002892984,"about_ca_topic_score_gemma":0.001007682,"domain_scores_codex":[0.9980531,0.00116476,0.00008215931,0.0002696892,0.0002734729,0.0001567085],"domain_scores_gemma":[0.9052645,0.08869249,0.001918011,0.001489914,0.001615816,0.001019297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003687933,0.0001766221,0.003436276,0.0002450743,0.0001630906,0.0003478685,0.0006320074,0.3232863,0.004297874,0.6219134,0.001833727,0.04329897],"study_design_scores_gemma":[0.00003012675,0.0001066268,0.000650236,0.00002410646,0.00003535899,0.00008362231,0.00004504328,0.7651606,0.0008297104,0.2325018,0.0005118537,0.00002097308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3209641,0.002119686,0.6342963,0.004046099,0.0001821247,0.00009175396,0.00008630196,0.0004470279,0.03776666],"genre_scores_gemma":[0.9811665,0.0003415353,0.01527552,0.0001558365,0.00007320868,0.00003792858,0.00001706524,0.00005537978,0.002877008],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004593015,"threshold_uncertainty_score":0.02302909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02194920132953579,"score_gpt":0.2696648351070748,"score_spread":0.2477156337775391,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}